CircleGuardBench

Evals

Benchmark / dataset

Benchmark for guard models (accuracy, speed, evasion).

Category
Guardrails & safety classifiers (adjacent)
Insurance exposure
Regulatory/bias
Publisher
White Circle AI
Publisher type
Company (open source)
License
Apache-2.0
Status
Maintained (<12mo)
Last commit
2026-03-07
Stars
81

View source on GitHub →

Wanich Risk Lab, 2026.